Non-Parametric Test Chooser
Decide when to avoid normality assumptions.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Help me choose between parametric and non-parametric tests. My data description and sample sizes: [DATA_SAMPLE]. Question: [QUESTION]. Explain the assumptions of the usual tests and how to check them (plots first, then tests, and why tests alone mislead). Provide a decision tree for my case, suggest the alternative test if assumptions fail (for example Mann-Whitney, Wilcoxon signed-rank, Kruskal-Wallis), and explain what each alternative actually compares. Include code for the checks and the test, effect sizes, and a note on reporting. Warn about common errors such as using non-parametric tests only when the parametric result is disappointing. Add a worked example with two small invented samples, showing both the parametric and non-parametric results and how to describe them. Include a short explanation of permutation tests as another option and a checklist for deciding whether the sample is too small for any of these tests. Also add a one-line reminder to state which test was used and why in any report, so that readers can judge it.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.